def ica(self, n_comp, data=None):
if data is None:
data = self.train
# Initializing the PCA instance with a percentage is telling the algorithm how much variance we wish to keep within the
# dataset. Dropping below 80% we would be losing a lot of data
ica_features = ICA(n_comp)
ica_features.fit(data)
self.ica_train_data = ica_features.transform(data)
self.ICA = ica_features
ica_test = ICA(n_comp)
ica_test.fit(self.test)
self.ica_test_data = ica_test.transform(self.test)
def ica(tx, ty, rx, ry, dataset):
reduced_data = ICA(n_components=2).fit_transform(tx)
em(tx, ty, rx, ry, reduced_data, add="", times=4, dataset=dataset, alg="ICA")
x,y = tx.shape
for i in range(0, y):
print(kurtosis(tx[:,i], fisher=False))
compressor = ICA(n_components = tx[1].size/2, max_iter=10000, tol=0.001) # for some people, whiten needs to be off
compressor.fit(tx, y=ty)
newtx = compressor.transform(tx)
newrx = compressor.transform(rx)
# km(newtx, ty, newrx, ry, [], add="", times=7, dataset=dataset, alg="ICA")
# Store results of PCA in a data frame
pca = ICA(n_components=2)
pca.fit(tx)
result=pd.DataFrame(pca.transform(tx), columns=['PCA%i' % i for i in range(2)])
my_color = pd.Series(ty).astype('category').cat.codes
fig = plt.figure()
# ax = fig.add_subplot(111, projection='2d')
ax = fig.add_subplot(111)
ax.scatter(result['PCA0'], result['PCA1'], c=my_color, cmap="Dark2_r", s=60)
plt.show()
result=pd.DataFrame(compressor.transform(tx), columns=['ICA%i' % i for i in range(3)])
my_color = pd.Series(ty).astype('category').cat.codes
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
ax.scatter(result['ICA0'], result['ICA1'], result['ICA2'], c=my_color, cmap="Dark2_r", s=60)
xAxisLine = ((min(result['ICA0']), max(result['ICA0'])), (0, 0), (0,0))
ax.plot(xAxisLine[0], xAxisLine[1], xAxisLine[2], 'r')
yAxisLine = ((0, 0), (min(result['ICA1']), max(result['ICA1'])), (0,0))
ax.plot(yAxisLine[0], yAxisLine[1], yAxisLine[2], 'r')
zAxisLine = ((0, 0), (0,0), (min(result['ICA2']), max(result['ICA2'])))
ax.plot(zAxisLine[0], zAxisLine[1], zAxisLine[2], 'r')
ax.set_xlabel("IC1")
ax.set_ylabel("IC2")
ax.set_zlabel("IC3")
ax.set_title("ICA on the Phishing data set")
plt.show()
print("-----------")
x,y = newtx.shape
for i in range(0, y):
print(kurtosis(newtx[:,i], fisher=False))
em(newtx, ty, newrx, ry, add="wICAtr", times=21, dataset=dataset, alg="ICA")
em(newtx, ty, newrx, ry, ICA(n_components=2).fit_transform(tx), add="wICAtr", times=9, dataset=dataset, alg = "Ica")
nn(newtx, ty, newrx, ry, add="wICAtr")
myNN(newtx, ty, newrx, ry, "ica")
def reduce_dim(data, labels, n_components, **kwargs):
''' performs dimensionality reduction'''
if kwargs['method'] == 'pca':
matrix = data
#transformer = Normalizer()
#transformer.fit(matrix)
pca = PCA(n_components=n_components, svd_solver='full')
pca.fit(matrix)
#return pca.fit_transform(matrix)
#pass
return pca.transform(matrix)
if kwargs['method'] == 'lda':
transformer = Normalizer()
label = labels
matrix = data
transformer.fit(matrix)
lda = LDA(n_components=n_components)
lda.fit(transformer.transform(matrix), label)
return lda.transform(matrix)
#pass
if kwargs['method'] == 'ica':
matrix = data
ica = ICA(n_components=n_components, random_state=0)
return ica.fit_transform(matrix)
def ica_analysis(X, y, plot_path):
feat_cols = list(X)
df = X #pd.DataFrame(X,columns=feat_cols)
df['y'] = y
df['label'] = df['y'].apply(lambda i: str(i))
X, y = None, None
print('Size of the dataframe: {}'.format(df.shape))
# For reproducability of the results
#np.random.seed(42)
#rndperm = np.random.permutation(df.shape[0])
label_list = df['y'].tolist()
label_list = list(map(int, label_list))
print(label_list)
ica = ICA(n_components=3)
ica_result = ica.fit_transform(df[feat_cols].values)
df['ica-one'] = ica_result[:, 0]
df['ica-two'] = ica_result[:, 1]
df['ica-three'] = ica_result[:, 2]
ax = plt.figure(figsize=(16, 10)).gca(projection='3d')
ax.scatter(xs=df["ica-one"],
ys=df["ica-two"],
zs=df["ica-three"],
c=label_list,
cmap='tab10')
ax.set_xlabel('ica-one')
ax.set_ylabel('ica-two')
ax.set_zlabel('ica-three')
plt.savefig(plot_path + '/ica_3D')
def reduce_dim(data,labels,n_components,**kwargs):
''' performs dimensionality reduction'''
if kwargs['method'] == 'pca':
matrix = data
pca = PCA(n_components=n_components)
pca.fit(matrix)
#return pca.fit_transform(matrix)
#pass
return pca.transform(matrix)
if kwargs['method'] == 'lda':
label = labels
matrix = data
lda = LDA(n_components = n_components)
lda.fit(matrix,label)
LDA(n_components= n_components, priors=None, shrinkage=None,
solver='svd', store_covariance=False, tol=0.0001)
#return lda.fit_transform(matrix,label)
return lda.transform(matrix)
pass
if kwargs['method'] == 'ica':
matrix = data
ica = ICA(n_components = n_components,random_state = 0)
return ica.fit_transform(matrix)
def split_ica(combined_data, label_1, label_2):
ica = ICA()
result = ica.fit(combined_data).transform(combined_data)
plt.plot(result[0:100, 0],
result[0:100, 1],
'o',
markersize=7,
color='blue',
alpha=0.5,
label=label_1)
plt.plot(result[100:200, 0],
result[100:200, 1],
'^',
markersize=7,
color='red',
alpha=0.5,
label=label_2)
plt.xlabel('x_values')
plt.ylabel('y_values')
plt.xlim([-0.3, 0.3])
plt.ylim([-0.3, 0.3])
plt.legend()
#plt.title('Transformed samples with class labels from matplotlib.mlab.PCA()')
plt.show()
return result
def ica(tx, ty, rx, ry):
compressor = ICA(whiten=True) # for some people, whiten needs to be off
newtx = compressor.fit_transform(tx)
newrx = compressor.fit_transform(rx)
em(newtx, ty, newrx, ry, add="wICAtr", times=10)
km(newtx, ty, newrx, ry, add="wICAtr", times=10)
nn(newtx, ty, newrx, ry, add="wICAtr")
def caller(tx, ty, rx, ry):
nums = [4,8,12,16]
for n in nums:
print("PCA")
print(n)
compressor = PCA(n_components = n)
compressor.fit(tx, y=ty)
newtx = compressor.transform(tx)
newrx = compressor.transform(rx)
nnTable(newtx, ty, newrx, ry, alg="PCA")
for n in nums:
print("ICA")
print(n)
compressor = ICA(n_components = n)
compressor.fit(tx, y=ty)
newtx = compressor.transform(tx)
newrx = compressor.transform(rx)
nnTable(newtx, ty, newrx, ry, alg="ICA")
for n in nums:
print("RandProj")
print(n)
compressor = RandomProjection(n)
compressor.fit(tx, y=ty)
newtx = compressor.transform(tx)
newrx = compressor.transform(rx)
nnTable(newtx, ty, newrx, ry, alg="PCA")
for n in nums:
print("kbest")
print(n)
compressor = best(k=n)
compressor.fit(tx, y=ty)
newtx = compressor.transform(tx)
newrx = compressor.transform(rx)
nnTable(newtx, ty, newrx, ry, alg="PCA")
def graphCallerNN(tx, ty, rx, ry):
n = tx[1].size/2
compressor = PCA(n_components = n)
compressor.fit(tx, y=ty)
newtx = compressor.transform(tx)
newrx = compressor.transform(rx)
newtx = oneem(newtx, ty, newrx, ry)
myNN(newtx, ty, newrx, ry, "EM-PCA")
# nnTable(newtx, ty, newrx, ry, alg="EM-PCA")
compressor = ICA(n_components = n)
compressor.fit(tx, y=ty)
newtx = compressor.transform(tx)
newrx = compressor.transform(rx)
newtx = oneem(newtx, ty, newrx, ry)
nnTable(newtx, ty, newrx, ry, alg="EM-ICA")
myNN(newtx, ty, newrx, ry, "EM-Ica")
compressor = RandomProjection(n)
compressor.fit(tx, y=ty)
newtx = compressor.transform(tx)
newrx = compressor.transform(rx)
newtx = oneem(newtx, ty, newrx, ry)
nnTable(newtx, ty, newrx, ry, alg="EM-RP")
myNN(newtx, ty, newrx, ry, "EM-RP")
compressor = best(k=n)
compressor.fit(tx, y=ty)
newtx = compressor.transform(tx)
newrx = compressor.transform(rx)
newtx = oneem(newtx, ty, newrx, ry)
nnTable(newtx, ty, newrx, ry, alg="EM-KB")
myNN(newtx, ty, newrx, ry, "EM-KB")
def ica_orth(A, r=None):
if r is None:
r = pca_rank_est(A)
I = ICA(n_components=r).fit(A.T)
P = I.transform(A.T)
K = A @ P
return K
def apply_ica():
cons = np.mat(np.zeros((data.shape[1], data.shape[1])))
for components in num_components:
pca = ICA(n_components=components)
X_r = pca.fit_transform(data.T)
cons += connectivity(data, X_r.T)
C = 1 - (cons / len(num_components))
return C, X_r
def credit_risk_data():
data_X = credit_data.drop([
'credit_amount', 'other_parties', 'purpose', 'own_telephone',
'foreign_worker'
],
axis=1)
data_y = credit_data[['class']]
features_to_encode = [
'personal_status', 'checking_status', 'credit_history',
'savings_status', 'employment', 'property_magnitude',
'other_payment_plans', 'housing', 'job', 'class'
]
enc = my_encoder()
enc.fit(data_X, features_to_encode)
X_train = enc.transform(data_X)
# X_test = enc.transform(X_test)
run_PCA(X_train, "Credit Data")
run_ICA(X_train, "Credit Data")
run_RCA(X_train, "Credit Data")
pca_credit = PCA(n_components=3, random_state=5).fit_transform(X_train)
ica_credit = ICA(n_components=2, random_state=5).fit_transform(X_train)
rca_credit = RCA(n_components=29, random_state=5).fit_transform(X_train)
run_kmeans(pca_credit, X_train, "KMEANS")
run_kmeans(ica_credit, X_train, "KMEANS")
run_kmeans(rca_credit, X_train, "KMEANS")
run_EM(pca_credit, X_train, 'PCA Credit Risk Data')
run_EM(ica_credit, X_train, 'ICA Credit Risk Data')
run_EM(rca_credit, X_train, 'RCA Credit Risk Data')
km = KMeans(n_clusters=3, random_state=0)
y_km = km.fit_predict(X_train)
score = silhouette_score(X_train, km.labels_, metric='euclidean')
print('Silhouetter Score: %.3f' % score)
# kmeans_silhoutte_analysis(X_train)
elbow_function(X_train)
run_kmeans(X_train, y_km, "KMEANS")
em = EM(n_components=2, covariance_type='spherical', random_state=100)
y_em = em.fit_predict(X_train)
plot_EM(em, X_train)
run_EM(X_train, y_em, "EM")
# evaluate_EM(em, X_train, y_em)
X_train, X_test, y_train, y_test = train_test_split(data_X,
data_y,
test_size=0.2,
random_state=0)
def ica(tx, ty, rx, ry):
compressor = ICA(whiten=True) # for some people, whiten needs to be off
newtx = compressor.fit_transform(tx)
newrx = compressor.fit_transform(rx)
kurtS = kurtosis(compressor.components_, axis = 1)
kurtIdx = np.argmax(kurtS)
print kurtS
print 'Kurtosis: ' +str(kurtS[kurtIdx])
# em(newtx, ty, newrx, ry, add="wICAtr", times=10)
# km(newtx, ty, newrx, ry, add="wICAtr", times=10)
nn(newtx, ty, newrx, ry, add="wICA")
def transform(X, factors, get_model, method, y=None):
if method == "raw" or method is None:
return X
if not factors or factors == "full":
factors = np.prod(X.shape[1:])
if method == "lda":
factors -= 1
if not isinstance(method, str):
raise RuntimeError("Please supply a method name (pca, lda, ica, cca, pls)")
method = method.lower()
if method == "pca":
from sklearn.decomposition import PCA
model = PCA(n_components=factors, whiten=True)
elif method == "lda":
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis as LDA
model = LDA(n_components=factors)
elif method == "ica":
from sklearn.decomposition import FastICA as ICA
model = ICA(n_components=factors)
elif method == "cca":
from sklearn.cross_decomposition import CCA
model = CCA(n_components=factors)
elif method == "pls":
from sklearn.cross_decomposition import PLSRegression as PLS
model = PLS(n_components=factors)
if str(y.dtype)[:3] not in ("flo", "int"):
y = dummycode(y, get_translator=False)
else:
raise ValueError("Method {} unrecognized!".format(method))
X = rtm(X)
if method in ("lda", "cca", "pls"):
if y is None:
raise RuntimeError("y must be supplied for {}!".format(method))
latent = model.fit_transform(X, y)
else:
if y is not None:
warnings.warn("y supplied for {}. Ignoring!".format(method))
latent = model.fit_transform(X)
if isinstance(latent, tuple):
latent = latent[0]
if get_model:
return latent, model
else:
return latent
def find_ica(self, n_comp, data=None):
if data is None:
data = self.train
ica_kutosis = pd.DataFrame()
ss = ShuffleSplit(n_splits=10, test_size=0.2)
for x in range(2, n_comp + 1):
ica_kutosis_train = 0
ica_kutosis_cv = 0
for train, cv in ss.split(self.train):
ica_features = ICA(n_components=x,
algorithm='parallel',
max_iter=500)
ica_features.fit(data.iloc[train])
ica_train_data = ica_features.transform(data.iloc[train])
ica_kutosis_train += np.sum(np.abs(kurtosis(ica_train_data)))
ica_features.fit(data.iloc[cv])
ica_cv_data = ica_features.transform(data.iloc[cv])
ica_kutosis_cv += np.sum(np.abs(kurtosis(ica_cv_data)))
ica_kutosis_train = ica_kutosis_train / 10
ica_kutosis_cv = ica_kutosis_cv / 10
ica_kutosis = ica_kutosis.append(
{
"K": x,
"Kurtosis_Train": ica_kutosis_train,
"Kurtosis_CV": ica_kutosis_cv
},
ignore_index=True)
print ica_kutosis
plt.plot(ica_kutosis["K"],
ica_kutosis["Kurtosis_Train"],
color='red',
label="Train")
plt.plot(ica_kutosis["K"],
ica_kutosis["Kurtosis_CV"],
color='blue',
label="CV")
plt.xlabel("N Components")
plt.ylabel("Absolute Sum Kurtosis")
plt.title("ICA: N Components vs Kurtosis")
plt.grid()
plt.legend()
plt.show()
def ICA_experiment(X, y, title, folder=""):
n_components_range = list(np.arange(2, X.shape[1], 1))
ica = ICA(random_state=200)
kurtosis_scores = []
for n in n_components_range:
ica.set_params(n_components=n)
ice_score = ica.fit_transform(X)
ice_score = pd.DataFrame(ice_score)
ice_score = ice_score.kurt(axis=0)
kurtosis_scores.append(ice_score.abs().mean())
plt.figure()
plt.title("ICA Kurtosis: " + title)
plt.xlabel("Independent Components")
plt.ylabel("Avg Kurtosis Across IC")
plt.plot(n_components_range, kurtosis_scores)
plt.savefig(folder + '/ICA.png')
plt.close()
def run_ICA(X, title):
dims = list(np.arange(2, (X.shape[1] - 1), 3))
dims.append(X.shape[1])
ica = ICA(random_state=5)
kurt = []
for dim in dims:
ica.set_params(n_components=dim)
tmp = ica.fit_transform(X)
tmp = pd.DataFrame(tmp)
tmp = tmp.kurt(axis=0)
kurt.append(tmp.abs().mean())
plt.figure()
plt.title("ICA Kurtosis: " + title)
plt.xlabel("Independent Components")
plt.ylabel("Avg Kurtosis Across IC")
plt.plot(dims, kurt, 'b-')
plt.grid(False)
plt.show()
def do_ica(data, class_label):
# ica
ica = ICA()
result = ica.fit(data).transform(data)
plt.plot(result[:, 0],
result[:, 1],
'o',
markersize=7,
color='blue',
alpha=0.5,
label=class_label)
plt.xlabel('x_values')
plt.ylabel('y_values')
plt.xlim([-0.5, 0.5])
plt.ylim([-0.5, 0.5])
plt.legend()
plt.title('Transformed samples versus original data')
plt.show()
def run_ICA(X, y, plot_path):
dims = list(np.arange(2, (X.shape[1] - 1), 3))
#dims = list(np.arange(2,80,3))
dims.append(X.shape[1])
ica = ICA(random_state=1, max_iter=10)
kurt = []
for dim in dims:
print(dim)
ica.set_params(n_components=dim)
tmp = ica.fit_transform(X)
tmp = pd.DataFrame(tmp)
tmp = tmp.kurt(axis=0)
kurt.append(tmp.abs().mean())
plt.figure()
plt.title("ICA Kurtosis")
plt.xlabel("Independent Components")
plt.ylabel("Avg Kurtosis Across IC")
plt.plot(dims, kurt, 'b-')
plt.grid(False)
plt.savefig(plot_path + '/ICA_DR')
def run_ICA(X, y, title):
dims = list(np.arange(2, (X.shape[1] - 1), 3))
dims.append(X.shape[1])
ica = ICA(random_state=randomSeed, whiten=True)
kurt = []
for dim in dims:
ica.set_params(n_components=dim)
tmp = ica.fit_transform(X)
tmp = pd.DataFrame(tmp)
tmp = tmp.kurt(axis=0)
kurt.append(tmp.abs().mean())
plt.figure()
plt.title("ICA Kurtosis: " + title)
plt.xlabel("Independent Components")
plt.ylabel("Avg Kurtosis Across IC")
plt.plot(dims, kurt, 'b-')
plt.grid(False)
d = plotsdir + "/" + title
if not os.path.exists(d):
os.makedirs(d)
plt.savefig(d + "/ICA Kurtosis.png")
X = []
y = []
for l in fin:
X.append(l.split(",")[:-2])
y.append(int(l.split(",")[-2]))
X = np.array(X,dtype=np.float32)
X = np.array(X,dtype=np.float32)
scaler = StandardScaler()
scaler.fit(X)
X = scaler.transform(X)
ica = ICA(n_components=4)
ica.fit(X)
X = ica.transform(X)
#plot_bic(X)
gmm = mixture.GaussianMixture(n_components=2,covariance_type='tied')
gmm.fit(X)
newX = []
for pt in X:
run_PCA(diabetes_X,diabetes_Y,"Diabetes Data") run_ICA(diabetes_X,diabetes_Y,"Diabetes Data") run_RCA(diabetes_X,diabetes_Y,"Diabetes Data") X_train, X_test, y_train, y_test = train_test_split(np.array(creditX),np.array(creditY), test_size=0.2) run_PCA(X_train,creditY,"Credit Data") run_ICA(X_train,creditY,"Credit Data") run_RCA(X_train,creditY,"Credit Data") imp_diabetes, topcols_diabetes = run_RFC(diabetes_X,diabetes_Y,df_diabetes) pca_diabetes = PCA(n_components=3,random_state=5).fit_transform(diabetes_X) ica_diabetes = ICA(n_components=5,random_state=5).fit_transform(diabetes_X) rca_diabetes = ICA(n_components=6,random_state=5).fit_transform(diabetes_X) rfc_diabetes = df_diabetes[topcols_diabetes] rfc_diabetes = np.array(rfc_diabetes.values,dtype='int64') run_kmeans(pca_diabetes,diabetes_Y,'PCA Diabetes Data') run_kmeans(ica_diabetes,diabetes_Y,'ICA Diabetes Data') run_kmeans(rca_diabetes,diabetes_Y,'RCA Diabetes Data') run_kmeans(rfc_diabetes,diabetes_Y,'RFC Diabetes Data') run_EM(pca_diabetes,diabetes_Y,'PCA Diabetes Data') run_EM(ica_diabetes,diabetes_Y,'ICA Diabetes Data') run_EM(rca_diabetes,diabetes_Y,'RCA Diabetes Data')
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import FastICA as ICA
import sklearn.model_selection as k
r=pd.read_csv('bank_contacts.csv')
x=r.drop('credit_application',axis=1)
y=r['credit_application']
train_x,test_x,train_y,test_y=k.train_test_split(x,y,test_size=0.2,random_state=42)
sc=StandardScaler()
train_x=sc.fit_transform(train_x)
test_x=sc.transform(test_x)
ica=ICA(n_components=4,random_state=42)
train_x=ica.fit_transform(train_x,train_y)
test_x=ica.transform(test_x)
from sklearn.ensemble import RandomForestClassifier
classifier = RandomForestClassifier(max_depth=2, random_state=0)
classifier.fit(train_x,train_y)
pred = classifier.predict(test_x)
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
print(confusion_matrix(test_y,pred))
print('Accuracy:',accuracy_score(test_y,pred))
plt.scatter(pred,test_x[:,0],marker='o')
plt.scatter(pred,test_x[:,1],marker='o')
plt.scatter(pred,test_x[:,2],marker='o')
plt.show()
ica = ICA(n_components = i)
Z = ica.fit_transform(X)
kur[i-1] = np.mean(kurtosis(Z))
scr[i-1] = np.amin(kurtosis(Z))
plt.plot(ks,kur,ks,scr)
plt.title("Adult Income Data - ICA")
plt.xlabel("# of components")
plt.ylabel("Score")
plt.legend(["kurtosis-avg",'kurtosis-min axis'])
plt.show()
"""
pca = ICA(n_components=6)
Z = pca.fit_transform(X)
for k in ks:
clust = KMeans(n_clusters=k).fit(Z)
W = clust.predict(Z)
ss[k - 1] = clust.inertia_
plt.plot(ks, ss)
plt.title("Wine Quality Data - KM")
plt.xlabel("# of clusters")
plt.ylabel("Sum of Squares")
plt.legend(["kmeans"])
plt.show()
for k in ks:
clust = GaussianMixture(n_components=k).fit(Z)
# play(song*3)
plt.plot(np.arange(1000)**2)
signal1 = np.sin(np.arange(256) * 0.15)
signal2 = np.sin(np.arange(256) * 0.06)
combinations = np.dot(np.random.random((200, 2)), np.vstack(
(signal1, signal2)))
combinations += np.random.random(combinations.shape) * .1
PCA_t = PCA(n_components=10)
PCA_t.fit(combinations)
ideal_n = np.where(np.cumsum(PCA_t.explained_variance_ratio_) > .99)[0][0] + 1
ICA_t = ICA(n_components=ideal_n, tol=1e-8)
scores = ICA_t.fit_transform(combinations)
mixings = ICA_t.mixing_
loadings = ICA_t.components_
# tops = mixings
plt.close()
fig, ax = plt.subplots(2, 2)
ax[0, 0].plot(signal1)
ax[0, 1].plot(signal2)
for i in range(combinations.shape[0]):
ax[1, 0].plot(combinations[i, :])
for i in range(loadings.shape[0]):
ax[1, 1].plot(loadings[i, :])
def separateComponents(self):
self.ica = ICA(n_components=len(self.signals[0]), max_iter=300)
self.components = np.matrix.transpose(
self.ica.fit_transform(self.signals))
self.amUnits = [np.amax(self.components), np.amin(self.components)]
self.selectedComponents = list(range(len(self.components)))
def get_ica_data(X, components):
return ICA(n_components=components,
random_state=randomSeed).fit_transform(X)
def main():
df = pd.read_csv("../Dataset/winequality-white.csv", delimiter=";")
seed = 200
np.random.seed(seed)
lowquality = df.loc[df['quality'] <= 6].index
highquality = df.loc[df['quality'] > 6].index
df.iloc[lowquality, df.columns.get_loc('quality')] = 0
df.iloc[highquality, df.columns.get_loc('quality')] = 1
X = np.array(df.iloc[:, 0:-1])
wine_Y = np.array(df.iloc[:, -1])
standardScalerX = StandardScaler()
wine_x = standardScalerX.fit_transform(X)
pca_wine = PCA(n_components=7, random_state=seed).fit_transform(wine_x)
ica_wine = ICA(n_components=9, random_state=seed).fit_transform(wine_x)
rca_wine = RCA(n_components=8, random_state=seed).fit_transform(wine_x)
imp_wine, top_columns_wine = run_RFC(wine_x, wine_Y, df)
rfc_wine = df[top_columns_wine]
rfc_wine = np.array(rfc_wine.values, dtype='int64')
X_train, X_test, y_train, y_test = train_test_split(np.array(wine_x),
np.array(wine_Y),
test_size=0.30)
learner = MLPClassifier(hidden_layer_sizes=(22, ),
activation='relu',
learning_rate_init=0.0051,
random_state=seed)
evaluate(learner, X_train, X_test, y_train, y_test, title="FullDataset")
X_train, X_test, y_train, y_test = train_test_split(np.array(pca_wine),
np.array(wine_Y),
test_size=0.30)
learner = MLPClassifier(hidden_layer_sizes=(22, ),
activation='relu',
learning_rate_init=0.0051,
random_state=seed)
evaluate(learner, X_train, X_test, y_train, y_test, title="PCA")
X_train, X_test, y_train, y_test = train_test_split(np.array(ica_wine),
np.array(wine_Y),
test_size=0.30)
learner = MLPClassifier(hidden_layer_sizes=(22, ),
activation='relu',
learning_rate_init=0.0051,
random_state=seed)
evaluate(learner, X_train, X_test, y_train, y_test, title="ICA")
X_train, X_test, y_train, y_test = train_test_split(np.array(rca_wine),
np.array(wine_Y),
test_size=0.30)
learner = MLPClassifier(hidden_layer_sizes=(22, ),
activation='relu',
learning_rate_init=0.0051,
random_state=seed)
evaluate(learner, X_train, X_test, y_train, y_test, title="RP")
X_train, X_test, y_train, y_test = train_test_split(np.array(rfc_wine),
np.array(wine_Y),
test_size=0.30)
learner = MLPClassifier(hidden_layer_sizes=(22, ),
activation='relu',
learning_rate_init=0.0051,
random_state=seed)
evaluate(learner, X_train, X_test, y_train, y_test, title="RFC")
ttX,ttY,bankX,bankY = import_data()
X_train, X_test, y_train, y_test = train_test_split(np.array(bankX),np.array(bankY), test_size=0.2)
run_PCA(X_train,y_train,"Banking Data")
#run_ICA(X_train,y_train,"Banking Data")
#run_RCA(bankX,bankY,"Banking Data")
#imp_bank, topcols_bank = run_RFC(X_train,y_train,df_bank)
#imp_bank
# In[15]:
ttX,ttY,bankX,bankY = import_data()
imp_tt, topcols_tt = run_RFC(ttX,ttY,df_tt)
pca_tt = PCA(n_components=10,random_state=5).fit_transform(ttX)
ica_tt = ICA(n_components=38,random_state=5).fit_transform(ttX)
rca_tt = ICA(n_components=29,random_state=5).fit_transform(ttX)
rfc_tt = df_tt[topcols_tt]
rfc_tt = np.array(rfc_tt.values,dtype='int64')
# In[26]:
print('pca')
run_kmeans(pca_tt,ttY,'PCA titanic Data')
print('ica')
run_kmeans(ica_tt,ttY,'ICA titanic Data')
print('rca')
run_kmeans(rca_tt,ttY,'RCA titanic Data')
print('rfc')
run_PCA(loanX, loanY, "Loan Data")
run_ICA(loanX, loanY, "Loan Data")
run_RCA(loanX, loanY, "Loan Data")
imp_loan, topcols_loan = run_RFC(loanX, loanY, df_loan)
loanX, loanY, telescopeX, telescopeY = import_data()
run_PCA(telescopeX, telescopeY, "Telescope Data")
run_ICA(telescopeX, telescopeY, "Telescope Data")
run_RCA(telescopeX, telescopeY, "Telescope Data")
imp_telescope, topcols_telescope = run_RFC(telescopeX, telescopeY,
df_telescope)
loanX, loanY, telescopeX, telescopeY = import_data()
imp_loan, topcols_loan = run_RFC(loanX, loanY, df_loan)
pca_loan = PCA(n_components=4, random_state=5).fit_transform(loanX)
ica_loan = ICA(n_components=8, random_state=5).fit_transform(loanX)
rca_loan = ICA(n_components=6, random_state=5).fit_transform(loanX)
rfc_loan = df_loan[topcols_loan]
rfc_loan = np.array(rfc_loan.values, dtype='int64')
run_kmeans(pca_loan, loanY, 'PCA loan Data')
run_kmeans(ica_loan, loanY, 'ICA loan Data')
run_kmeans(rca_loan, loanY, 'RCA loan Data')
run_kmeans(rfc_loan, loanY, 'RFC loan Data')
evaluate_kmeans(KMeans(n_clusters=10, n_init=10, random_state=100, n_jobs=-1),
pca_loan, loanY)
evaluate_kmeans(KMeans(n_clusters=10, n_init=10, random_state=100, n_jobs=-1),
ica_loan, loanY)
evaluate_kmeans(KMeans(n_clusters=5, n_init=10, random_state=100, n_jobs=-1),
rca_loan, loanY)